Video Generation

Generate videos from text prompts or input images using Fluxpool's unified API. Supports 5+ video models through a single endpoint.

Overview #

Video generation is asynchronous. Unlike image generation, video models take 30–120 seconds to produce output. The flow is:

1. Submit a generation request → receive a generation_id
2. Poll the status endpoint or receive a webhook callback when complete
3. Retrieve the video URL from the completed response

Endpoint #

Request Body #

Text-to-Video #

Generate a video from a text prompt.

{
  "model": "wan-video-2.1",
  "prompt": "A drone shot flying through cherry blossom trees, slow motion, cinematic lighting",
  "duration": 5,
  "resolution": "1280x720",
  "webhook_url": "https://your-app.com/api/webhook"
}

Image-to-Video #

Animate a static image into a video. Pass an image URL or base64 in place of (or alongside) prompt.

{
  "model": "kling-v2",
  "prompt": "Camera slowly zooms out, leaves rustling in wind",
  "image": "https://your-bucket.s3.amazonaws.com/input-image.png",
  "duration": 5,
  "resolution": "1080p",
  "webhook_url": "https://your-app.com/api/webhook"
}

Available Models #

Full model details, parameters, and sample outputs: Browse all models →

Response #

A successful request returns a generation object with status processing.

{
  "id": "gen_abc123xyz",
  "status": "processing",
  "model": "wan-video-2.1",
  "created_at": "2025-01-15T10:30:00Z",
  "estimated_completion": "2025-01-15T10:30:45Z",
  "output": null
}

When complete, the output field populates:

{
  "id": "gen_abc123xyz",
  "status": "completed",
  "model": "wan-video-2.1",
  "created_at": "2025-01-15T10:30:00Z",
  "completed_at": "2025-01-15T10:30:43Z",
  "output": {
    "url": "https://cdn.fluxpool.ai/v/gen_abc123xyz.mp4",
    "duration": 5,
    "resolution": "1280x720",
    "format": "mp4",
    "size_bytes": 4821504
  }
}

Possible status values:

Polling for Results #

If you're not using webhooks, poll the status endpoint:

import time
from openai import OpenAI

client = OpenAI(
    base_url="https://api.fluxpool.ai/v1",
    api_key="fp_your_api_key"
)

# Submit generation
generation = client.videos.generate(
    model="wan-video-2.1",
    prompt="A koi fish transforming into a phoenix, slow motion"
)

# Poll until complete
while generation.status == "processing":
    time.sleep(5)
    generation = client.videos.retrieve(generation.id)

print(generation.output.url)

Using Webhooks #

Send a webhook_url in your request. Fluxpool will POST the completed generation object to your URL when the video is ready.

{
  "model": "kling-v2",
  "prompt": "Timelapse of a flower blooming in a dark room, dramatic lighting",
  "duration": 5,
  "webhook_url": "https://your-app.com/api/fluxpool-webhook"
}

Your webhook endpoint will receive:

{
  "event": "generation.completed",
  "data": {
    "id": "gen_abc123xyz",
    "status": "completed",
    "model": "kling-v2",
    "output": {
      "url": "https://cdn.fluxpool.ai/v/gen_abc123xyz.mp4",
      "duration": 5,
      "resolution": "1080p",
      "format": "mp4"
    }
  }
}

For webhook security, signature verification, and retry logic, see the full Webhooks documentation →

Code Examples #

from openai import OpenAI

client = OpenAI(
    base_url="https://api.fluxpool.ai/v1",
    api_key="fp_your_api_key"
)

# Text-to-Video
generation = client.videos.generate(
    model="wan-video-2.1",
    prompt="A cyberpunk city street in heavy rain, neon reflections, cinematic",
    duration=5,
    resolution="1280x720",
    webhook_url="https://your-app.com/api/webhook"  # optional
)

print(f"Generation ID: {generation.id}")
print(f"Status: {generation.status}")

# Image-to-Video
generation = client.videos.generate(
    model="kling-v2",
    prompt="Camera slowly orbits the subject, shallow depth of field",
    image="https://your-bucket.s3.amazonaws.com/photo.png",
    duration=5
)

# Text-to-Video
curl https://api.fluxpool.ai/v1/videos/generations \
  -H "Authorization: Bearer fp_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-video-2.1",
    "prompt": "A cyberpunk city street in heavy rain, neon reflections, cinematic",
    "duration": 5,
    "resolution": "1280x720"
  }'

# Poll for result
curl https://api.fluxpool.ai/v1/videos/generations/gen_abc123xyz \
  -H "Authorization: Bearer fp_your_api_key"

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.fluxpool.ai/v1",
  apiKey: "fp_your_api_key",
});

// Text-to-Video
const generation = await client.videos.generate({
  model: "wan-video-2.1",
  prompt: "A cyberpunk city street in heavy rain, neon reflections, cinematic",
  duration: 5,
  resolution: "1280x720",
  webhook_url: "https://your-app.com/api/webhook",
});

console.log(`Generation ID: ${generation.id}`);
console.log(`Status: ${generation.status}`);

// Poll for result
const checkStatus = async (id) => {
  let result = await client.videos.retrieve(id);
  while (result.status === "processing") {
    await new Promise((r) => setTimeout(r, 5000));
    result = await client.videos.retrieve(id);
  }
  return result;
};

const completed = await checkStatus(generation.id);
console.log(completed.output.url);

Parameters Reference #

Full list of request body parameters.

Error Handling #

If a generation fails, the response status will be "failed" with an error object:

{
  "id": "gen_abc123xyz",
  "status": "failed",
  "model": "wan-video-2.1",
  "error": {
    "code": "content_policy_violation",
    "message": "The prompt was flagged by the content safety filter."
  }
}

Common error codes:

Cost & Billing #

Each video generation deducts credits from your account balance. Cost varies by model, duration, and resolution.

Credits are deducted when generation begins. If a generation fails, credits are refunded automatically.

See full pricing details →

Rate Limits #

Rate limit headers are included in every response:

X-RateLimit-Limit: 20
X-RateLimit-Remaining: 17
X-RateLimit-Reset: 1705312200

If you exceed the limit, you'll receive a 429 Too Many Requests response. Implement exponential backoff.

Need higher limits? Contact us →

Related #